Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2020-06-07 000000m 11:51:39 - Overview

Attribute Current Content New
Name (Institute + Shorttitle)VSUMM (Video SUMMarization) 
Description (include details on usage, files and paper references)The VSUMM (Video SUMMarization) dataset is of 50 videos from Open Video. All videos are in MPEG-1 format (30 fps, 352 x 240 pixels), in color and with sound. These videos are distributed among several genres (documentary, educational, ephemeral, historical, lecture) and their duration varies from 1 to 4 minutes and approximately 75 minutes of video in total.

It also contains 250 user summaries. These summaries were created manually by 50 users, each one dealing with 5 videos, meaning that each video has 5 video summaries created by 5 different users.  
URL Link 
Files (#)250 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)video summary type user study keyframe static similarity 
Last Changed2020-06-07 
Turing (2.12+3.25=?) :-)